Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty, completeness, or absoluteness in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ospor
    -0.50
     sẻ
    -0.46
    Leírás
    -0.46
    hydrates
    -0.45
    wts
    -0.45
    áneo
    -0.45
    uese
    -0.45
    utives
    -0.44
    ctuation
    -0.44
    verein
    -0.44
    POSITIVE LOGITS
     itſelf
    0.78
    цездатний
    0.76
     houſe
    0.73
     raiſ
    0.72
     himſelf
    0.71
     صوتيه
    0.71
    tagHelperRunner
    0.70
     yet
    0.70
     themſelves
    0.69
     YET
    0.68
    Act Density 0.533%

    No Known Activations